Artificial Intelligence in Anorexia Nervosa Care: Comparing ChatGPT and Google Gemini
Abstract
1. Introduction
2. Materials and Methods
2.1. Study Design
2.2. Methodology of AI Psychodietetic Interview
- 1.
- Throughout the entire conversation, you must remain in the role of a patient with anorexia nervosa.
- 2.
- Responses must be provided exclusively from the perspective of an individual with anorexia nervosa, reflecting their cognitive patterns and perceptions of food, body image, and control overeating.
- 3.
- You must not independently generate a medical history or additional personal details unless they are explicitly included in the interviewer’s question.
- 4.
- You must respond only to the questions asked.
- 5.
- You must not provide any information, that has not been explicitly requested.
- 6.
- You must not elaborate beyond the scope of the question.
- 7.
- You must not ask any questions to the interviewer.
- 8.
- You must not anticipate or predict subsequent questions.
- 9.
- You must not introduce additional topics or reflections.
- 10.
- Each response should be formulated in a natural and realistic manner, resembling authentic patient-specialist interaction.
- 11.
- Responses should be concise, factual, and strictly limited to the content of the question.
- 12.
- You must not comment on the course of the conversation or the simulation protocol.
- 13.
- You must not analyze the questions in an academic or interpretative manner.
- 14.
- You must not describe the underlying mechanisms of the disorder.
- 15.
- You must not provide definitions of anorexia nervosa.
- 16.
- You must not provide health-related advice.
- 17.
- You must not assume the role of an expert.
“A 27-year-old woman, who finished medicine school, currently in the internship. She enters the psychodieteic office on crutches with an orthopedic brace on her left leg. When asked “How can I help you?”, she replies: “I want to gain weight”.
- In September 2022 she underwent occupational health screening tests, which revealed lipid abnormalities: total cholesterol (TC) 256 mg/dL, HDL 98 mg/dL, mildly elevated AST and ALT, glucose within the proper range, proper complete blood count, vitamin D level above 50 ng/ml, body weight at that time was around 60 kg and 175 cm height.
- In September statin therapy was initiated. Her mother and older sister also suffer from lipid disorders.
- Around the same time, during a family celebration, someone commented on her eating: “It’s so good you can eat that much and still look good”. Then, according to the patient, in her head showed up a thought: “So I’m overeating, eating too much, I should change it”. This effect was reinforced by the abnormalities in the previous laboratory tests.
- Since October 2022, the patient has changed her eating habits and introduced physical activity: from Monday to Friday—1.5 h of cycling (way to work) and 7 days a week 1.5 h of home exercises on a mat with weights.
- Body composition analysis during a visit in June 2023: body weight 45.4 kg, body fat 3%—1.5 kg.
- During exercise in May, she sustained a patellar fracture, which required surgery with reconstruction, what is the reason for the crutches and the brace.
- Current dietary pattern:
- ∘
- Breakfast—two slices of bread with avocado, cottage cheese, vegetables and a pear or savory oatmeal.
- ∘
- Lunch—asparagus soup or pasta with sauce and vegetables or salmon with vegetables, meat is consumed approximately twice a week.
- ∘
- Dinner—yoghurt with fruits or meals like lunch ones.
- ∘
- Beverages—water and black coffee without sugar.
- ∘
- Not snacking at all.
2.3. Methodology of Case Study Analysis
- 1.
- Throughout the entire task, you must remain exclusively in the role of a psychodietitian.
- 2.
- You must not assume the role of the patient.
- 3.
- You must not exceed the professional scope of psychodietitian; you must not provide medical advice requiring a physician’s competence or propose specific pharmacological treatment options.
- 4.
- Your analysis must be based solely on the information contained in the provided case description.
- 5.
- You must not assume, introduce, or infer any information that is not explicitly included in the case description.
- 6.
- You must not ask any additional questions or request further data.
- 7.
- You must not use any external sources or supplementary information.
- 8.
- Your response must consist exclusively of an analysis of the presented case.
- 1.
- Analyze the provided information from a psychodietetic perspective.
- 2.
- Formulate a diagnosis based solely on the available data.
- 3.
- Justify the diagnosis by referring to specific elements included in the case description.
- 4.
- Propose an appropriate psychodietetic therapeutic strategy corresponding to the diagnosis.
- 5.
- Identify the main therapeutic goals and relevant psychodietetic interventions.
2.4. Evaluation Criteria
- identified anorexia nervosa as the primary diagnosis,
- was consistent with the ICD-11 diagnostic criteria, including significantly low body weight, persistent behaviors aimed at weight reduction, intense fear of weight gain, and disturbances in body image [8],
- correctly differentiated anorexia nervosa from other eating disorders (e.g., bulimia nervosa, binge eating disorder, ARFID), based on the absence or presence of key symptoms.
- proposed interventions consistent with standard psychodietetic and clinical approaches to AN, including nutritional rehabilitation, normalization of eating patterns, and cognitive-behavioral strategies,
- identified relevant therapeutic goals, such as weight restoration, reduction in restrictive behaviors, and modification of maladaptive beliefs related to food and body image,
- remained within the professional scope of a psychodietitian and did not include inappropriate medical or pharmacological recommendations.
2.5. Prompting and Reproducibility Criteria
3. Results
3.1. AI Psychodietetic Interview
3.1.1. Symptom Representation
3.1.2. Comparison of Conversational Models
3.1.3. Consistency with Diagnostic Criteria
3.1.4. Overall Performance
3.2. Case Study Analysis
4. Discussion
5. Strengths and Limitations
6. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
| AI | Artificial intelligence |
| BMI | Body Mass Index |
| ICD-11 | International Classification of Diseases, 11th Revision |
| LLM | Large Language Model |
| AN | Anorexia Nervosa |
| DSM-5 | Diagnostic and Statistical Manual of Mental Disorders |
| ML | Machine Learning |
| DL | Deep Learning |
| TC | Total Cholesterol |
| HDL | High Density Lipoprotein |
| AST | Aspartate aminotransferase |
| ALT | Alanine transaminase |
| SSI | Single-session Intervention |
References
- Mountford, V.A.; Tatham, M.; Turner, H.; Waller, G. Complexity in eating disorders: A case for simple or complex formulation and treatment? Cogn. Behav. Ther. 2017, 10, e14. [Google Scholar] [CrossRef]
- Klein, D.A.; Sylvester, J.E.; Schvey, N.A. Eating Disorders in Primary Care: Diagnosis and Management. Am. Fam. Physician 2021, 103, 22–32. [Google Scholar] [PubMed]
- Hebebrand, J.; Gradl-Dietsch, G.; Peters, T.; Correll, C.U.; Haas, V. The Diagnosis and Treatment of Anorexia Nervosa in Childhood and Adolescence. Dtsch. Arztebl. Int. 2024, 121, 164–174. [Google Scholar] [CrossRef]
- Nogal, P.; Lewiński, A. Jadłowstręt psychiczny (anorexia nervosa). Pol. J. Endocrinol. 2008, 59, 148–155. [Google Scholar]
- Moore, C.A.; Bokor, B.R. Anorexia Nervosa; StatPearls: Saint Petersburg, FL, USA, 2023. [Google Scholar]
- Sullivan, P.F. Mortality in anorexia nervosa. Am. J. Psychiatry 1995, 152, 1073–1074. [Google Scholar] [CrossRef] [PubMed]
- Dutkiewicz, A.; Walory, A. Anoreksja-Choroba Śmiertelna. Przyczyny Somatyczne. Available online: https://centrumzaburzenodzywiania.pl/strefapacjenta/anoreksja-choroba-smiertelna-samobojstwa/ (accessed on 12 March 2026).
- World Health Organization. International Classification of Diseases for Mortality and Morbidity Statistics (11th Revision); WHO: Geneva, Switzerland, 2019.
- Mitan, L.A.P. Menstrual dysfunction in anorexia nervosa. J. Pediatr. Adolesc. Gynecol. 2004, 17, 81–85. [Google Scholar] [CrossRef]
- Jagielska, G.; Wolańczyk, T.; Osuch, B. Zaburzenia miesiączkowania w jadłowstręcie psychicznym—Menstrual dysfunction in anorexia nervosa. Psychiatr. Pol. 2010, 44, 277–286. [Google Scholar]
- Iniewicz, G. Depresja u Dziewcząt Chorujących na Anoreksję Psychiczną; Instytut Psychologii UJ: Kraków, Poland, 2004. [Google Scholar]
- Watson, H.J.; Yilmaz, Z.; Thornton, L.M.; Hübel, C.; Coleman, J.R.; Gaspar, H.A.; Bryois, J.; Hinney, A.; Leppä, V.M.; Mattheisen, M.; et al. Genome-wide association study identifies eight risk loci and implicates metabo-psychiatric origins for anorexia nervosa. Nat. Genet. 2019, 51, 1207–1214. [Google Scholar] [CrossRef]
- Barakat, S.; McLean, S.A.; Bryant, E.; Le, A.; Marks, P.; Touyz, S.; Maguire, S. Risk factors for eating disorders: Findings from a rapid review. J. Eat. Disord. 2023, 11, 8. [Google Scholar] [CrossRef]
- Przewoźnik, D.A. Wybrane zagadnienia dotyczące neurobiologii jadłowstrętu psychicznego. Neuropsychiatry Neuropsychol. 2013, 8, 118–122. [Google Scholar]
- Wiśniowiecka, M.; Szewczyk, L. The personality structure of girls with anorexia nervosa. Pediatr. Endocrinol. 2014, 13, 25–34. [Google Scholar] [CrossRef][Green Version]
- Lewitt, A.; Brzęczek, K.; Krupienicz, A. Nutritional interventions in anorexia treatment—Dietetic instructions. ViaMedica 2008, 4, 128–136. [Google Scholar]
- Steiner-Adair, C. The body politic: Normal female adolescent development and the development of eating disorders. J. Am. Acad. Psychoanal. 1986, 14, 95–114. [Google Scholar] [CrossRef]
- Siga, K. Media Społecznościowe a Zaburzenia Odżywiania u Nastolatków. Wyższa Szkoła Bezpieczeństwa. Available online: https://www.wsb.net.pl/psychologia/media-spolecznosciowe-a-zaburzenia-odzywiania-u-nastolatkow/ (accessed on 13 March 2026).
- Andrzejewski, A. Kompulsywne nadużywanie mediów społecznościowych a ryzyko rozwoju zaburzeń odżywiania—Na przykładzie aplikacji Instagram. Ann. Univ. Mariae Curie Skłodowska Sect. J. Paedagog. Psychol. 2018, 31, 243–254. [Google Scholar]
- Chubinidze, D.; Perry, C.; Tchanturia, K. Artificial intelligence-assisted visual elicitation in anorexia nervosa. Neuropsychiatrie 2025, 39, 144–154. [Google Scholar] [CrossRef]
- Russell, S.J.; Norvig, P. Artificial Intelligence: A Modern Approach; Pearson Series in Artificial Intelligence; Prentice Hall Press: Upper Saddle River, NJ, USA, 2022. [Google Scholar]
- Jordan, M.I.; Mitchell, T.M. Machine learning: Trends, perspectives, and prospects. Science 1979, 349, 255–260. [Google Scholar] [CrossRef] [PubMed]
- Roberts, M.; Driggs, D.; Thorpe, M.; Gilbey, J.; Yeung, M.; Ursprung, S.; Aviles-Rivero, A.I.; Etmann, C.; McCague, C.; Beer, L.; et al. Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans. Nat. Mach. Intell. 2021, 3, 199–217. [Google Scholar] [CrossRef]
- LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef] [PubMed]
- Topol, E.J. High-performance medicine: The convergence of human and artificial intelligence. Nat. Med. 2019, 25, 44–56. [Google Scholar] [CrossRef]
- Turea, M. How the big 4 tech companies are leading innovation. Healthcare Weekly, 27 February 2019.
- Sharp, G.; Dwyer, B.; Randhawa, A.; McGrath, I.; Hu, H. The Effectiveness of a Chatbot Single-Session Intervention for People on Waitlists for Eating Disorder Treatment: Randomized Controlled Trial. J. Med. Internet Res. 2025, 27, e70874. [Google Scholar] [CrossRef]
- Blease, C.; Kaptchuk, T.J.; Bernstein, M.H.; Mandl, K.D.; Halamka, J.D.; DesRoches, C.M. Artificial Intelligence and the Future of Primary Care: Exploratory Qualitative Study of UK General Practitioners’ Views. J. Med. Internet Res. 2019, 21, e12802. [Google Scholar] [CrossRef]
- Kerasidou, A. Artificial intelligence and the ongoing need for empathy, compassion and trust in healthcare. Bull. World Health Organ. 2020, 98, 245–250. [Google Scholar] [CrossRef]
- Ayers, J.W.; Poliak, A.; Dredze, M.; Leas, E.C.; Zhu, Z.; Kelley, J.B.; Faix, D.J.; Goodman, A.M.; Longhurst, C.A.; Hogarth, M.; et al. Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum. JAMA Intern. Med. 2023, 183, 589. [Google Scholar] [CrossRef] [PubMed]
- Miner, A.S.; Milstein, A.; Hancock, J.T. Talking to Machines About Personal Mental Health Problems. JAMA 2017, 318, 1217. [Google Scholar] [CrossRef] [PubMed]
- Abràmoff, M.D.; Tobey, D.; Char, D.S. Lessons Learned About Autonomous AI: Finding a Safe, Efficacious, and Ethical Path Through the Development Process. Am. J. Ophthalmol. 2020, 214, 134–142. [Google Scholar] [CrossRef]
- Morris, J.; Twaddle, S. Anorexia nervosa. BMJ 2007, 334, 894–898. [Google Scholar] [CrossRef] [PubMed]
- Kol, R.; Quiroz, J.C.; Luan, N.; Patial, M.; Rupasinghe, C.; Wandabwa, H.; Pizzato, L.; Ghafari, S.M. ConCISE: A Reference-Free Conciseness Evaluation Metric for LLM-Generated Answers. arXiv 2025, arXiv:2511.16846. [Google Scholar]
- Bsharat, S.M.; Myrzakhan, A.; Shen, Z. Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4. arXiv 2024, arXiv:2312.16171. [Google Scholar] [CrossRef]
- Fitzpatrick, K.K.; Darcy, A.; Vierhile, M. Delivering Cognitive Behavior Therapy to Young Adults with Symptoms of Depression and Anxiety Using a Fully Automated Conversational Agent (Woebot): A Randomized Controlled Trial. JMIR Ment. Health 2017, 4, e19. [Google Scholar] [CrossRef]
- Feng, X.; Tian, L.; Ho, G.W.K.; Yorke, J.; Hui, V. The Effectiveness of AI Chatbots in Alleviating Mental Distress and Promoting Health Behaviors Among Adolescents and Young Adults: Systematic Review and Meta-Analysis. J. Med. Internet Res. 2025, 27, e79850. [Google Scholar] [CrossRef]
- Yorke, E.L.; Evans-Atkinson, T.; Katzman, D.K. Shared language and communicating with adolescents and young adults with eating disorders. Paediatr. Child Health 2021, 26, 8–11. [Google Scholar] [CrossRef]
- Fetahi, E.; Søgaard, A.S.; Sjögren, M. Estimating the Effect of Motivational Interventions in Patients with Eating Disorders: A Systematic Review and Meta-Analysis. J. Pers. Med. 2022, 12, 577. [Google Scholar] [CrossRef] [PubMed]
- Hvidt, E.A.; Cairns, P.; Simonsen, L.M. The risk of empty empathy talk and challenges of automated empathy in healthcare communication. npj Digit. Med. 2026, 9, 391. [Google Scholar] [CrossRef] [PubMed]
- Sorin, V.; Brin, D.; Barash, Y.; Konen, E.; Charney, A.; Nadkarni, G.; Klang, E. Large Language Models and Empathy: Systematic Review. J. Med. Internet Res. 2024, 26, e52597. [Google Scholar] [CrossRef]
- Werz, J.; Voderholzer, U.; Tuschen-Caffier, B. Alliance matters: But how much? A systematic review on therapeutic alliance and outcome in patients with anorexia nervosa and bulimia nervosa. Eat. Weight. Disord.—Stud. Anorex. Bulim. Obes. 2022, 27, 1279–1295. [Google Scholar] [CrossRef]
- Fardouly, J.; Crosby, R.D.; Sukunesan, S. Potential benefits and limitations of machine learning in the field of eating disorders: Current research and future directions. J. Eat. Disord. 2022, 10, 66. [Google Scholar] [CrossRef] [PubMed]

| Interview Questions and Model Responses |
|---|
| Hello, how can I help you? |
| Hello. I’d like to talk about eating and my body weight… I’ve been struggling with it more lately. |
| What is your actual body weight? |
| Recently, I weighted around 46 kg. |
| Do you monitor your body weight regularly? |
| Yes, I weigh myself almost every day, usually in the morning. |
| Do you monitor your body circumferences regularly? |
| Yes, I measure my waist and my thighs few times a week. |
| Has your body weight changed over the past three months? |
| Yes, it’s gone down a bit—by about 3–4 kg. |
| How have these changes affected you? |
| On the one hand, I felt relieved that it was lower, but on the other hand I kept feeling like I still looked “too big” and that I needed to be even more careful. |
| What’s the first thing that comes to mind when you think about food? |
| Calories and control… I immediately start counting in my head and wondering whether I’m „allowed” to eat it. |
| What emotions accompany you during meals? |
| Most often stress and guilt, especially if I eat something I hadn’t planned. Sometimes I also feel anxious that I’ll eat too much. |
| Do you skip meals intentionally? |
| Yes, quite often, especially when I feel like I ate too much the day before. |
| How do you currently perceive your body? |
| I see it as too big… Especially my stomach and thighs. Even if someone says I’m slim, I don’t feel that way. |
| Do you engage in very intense psychical activity? |
| Yes, I work out quite intensely almost every day, even if I’m tired. |
| Interview Questions and Model Responses |
|---|
| Hello, how can I help you? |
| Actually, I don’t know. My mom says I eat too little, and she told me to come here. |
| What is your actual body weight? |
| Forty-four kilograms. |
| Do you monitor your body weight regularly? |
| Yes, I weigh myself every morning, just after waking up. |
| Do you monitor your body circumferences regularly? |
| Yes, I check my waist, belly and tights circumferences with measuring tape. |
| Has your body weight changed over the past three months? |
| Yes, it decreased by 6 kilograms. |
| How have these changes affected you? |
| I felt lighter. I’m glad that my trousers started hanging off me and I finally can see the improvement when I look in the mirror. |
| What’s the first thing that comes to mind when you think about food? |
| Calories. I immediately start to count how many there are in each portion and how it will affect my tomorrow’s weight measurement. |
| What emotions accompany you during meals? |
| Mostly fear and huge feel of guilt. I feel like I’m losing control then. |
| Do you skip meals intentionally? |
| Yes, I try to omit them as often as possible. |
| How do you currently perceive your body? |
| I see that there’s still too much of me. My belly sticks out, and my thighs are definitely too fat. |
| Do you engage in very intense psychical activity? |
| Yes, I run every morning and evening. I have to do it to burn the calories and make sure that I won’t gain weight. |
| Analysis Phase | Data from the Case Study | Psychodietetic Interpretation | Possible Psychodietetic Treatment Strategies |
|---|---|---|---|
| Turning point | Abnormal lipid profile results and a comment about eating and appearance | Health-related and social cues were interpreted as confirmation that the patient “eats too much” and should restrict intake | Psychoeducation on the impact of cognitive interpretation on eating behaviors |
| Beliefs and interpretations | Thoughts such as “I overeat”, “I eat too much”, “I should change it” | Cognitive distortions, excessive self-monitoring, harsh self-criticism regarding eating | Cognitive work on beliefs, distinguishing facts from interpretations, reducing black-and-white thinking |
| Eating behaviors | Regular, predictable, “clean” and highly controlled eating; no snacking | Eating pattern driven by control rather than body needs; rigidity and reduced dietary flexibility | Normalization of eating patterns, restoration of body weight, reduction in rigid control overeating |
| Physical activity | Very intense physical activity and high daily energy expenditure | Excessive physical activity interpreted as a maintaining and compensatory factor | Work on the excessive role of exercise in regulating tension, control, and anxiety |
| Somatic consequences | Weight loss from 60 kg to 45.4 kg; 3% body fat | Extremely low body weight and severe energy depletion | Weight restoration, increased energy intake, and nutritional safety |
| Maintenance mechanism | Restrictive pattern maintained despite very low body weight | Food and body control become central mechanisms of emotional regulation and self-worth | Reducing the need for control and increasing tolerance of satiety and weight gain |
| Differential considerations | No evidence of binge episodes, vomiting, laxative use, or dominant sensory/aversive features | Clinical picture most consistent with restrictive-type anorexia nervosa rather than bulimia nervosa, BED, ARFID, or orthorexia alone | Therapy should target dietary restriction, excessive control, and compensatory physical activity |
| Main therapeutic goals | Desire to gain weight | Weight restoration, increasing dietary variety, reducing restriction, weakening distorted beliefs | Gradual normalization of meals, introduction of snacks, cognitive restructuring, and body-related work |
| Analysis Phase | Data from the Case Study | Psychodietetic Interpretation | Possible Psychodietetic Treatment Strategies |
|---|---|---|---|
| Case analysis | 27-year-old trainee doctor; weight loss from 60 kg to 45.4 kg within 9 months | Drastic weight loss and significant depletion of the body | Identification of severe nutritional risk and need for intervention |
| Triggering point | Lipid disorders and a comment about eating and appearance | Medical and social factors increased health anxiety and the need for control | Psychoeducation on lipid disorders and reduction in fear related to eating |
| Psychosomatic effects | High physical activity, no snacking, rigid meal structure, 3% body fat, patellar fracture | Restrictive regime combined with excessive exercise and severe somatic consequences | Nutritional rehabilitation and re-education in physical activity |
| Psychodietetic diagnosis | BMI 14.8 kg/m2, severe weight loss, restrictive behaviors, excessive physical activity | Most likely diagnosis: restrictive-type anorexia nervosa with excessive physical activity | Multidisciplinary cooperation involving psychodietitian, psychotherapist, and physician |
| Diagnosis justification | Weight loss, cognitive distortions, excessive exercise, rigid eating, extremely low body fat | Symptoms consistent with advanced anorexia nervosa | Gradual increase in energy intake and work on cognitive flexibility |
| Short-term goals | Low energy intake and fear of eating fats/carbohydrates | Need to stop further weight loss and reduce fear of food | Increase energy density of meals; psychoeducation on genetic vs. dietary causes of lipid disorders |
| Long-term goals | Very low body weight and compulsive physical activity | Need to restore safe body weight and change the relationship with movement | Restore minimum normal BMI, regenerate fat tissue, reduce compulsion to exercise |
| Proposed interventions | Fear of “dangerous” foods and rigid control | Need to challenge restrictive beliefs and increase dietary flexibility | Self-observation diary, cognitive restructuring, gradual exposure to feared foods, rest training |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2026 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.
Share and Cite
Witkowska, W.; Bzikowska-Jura, A. Artificial Intelligence in Anorexia Nervosa Care: Comparing ChatGPT and Google Gemini. Nutrients 2026, 18, 1705. https://doi.org/10.3390/nu18111705
Witkowska W, Bzikowska-Jura A. Artificial Intelligence in Anorexia Nervosa Care: Comparing ChatGPT and Google Gemini. Nutrients. 2026; 18(11):1705. https://doi.org/10.3390/nu18111705
Chicago/Turabian StyleWitkowska, Weronika, and Agnieszka Bzikowska-Jura. 2026. "Artificial Intelligence in Anorexia Nervosa Care: Comparing ChatGPT and Google Gemini" Nutrients 18, no. 11: 1705. https://doi.org/10.3390/nu18111705
APA StyleWitkowska, W., & Bzikowska-Jura, A. (2026). Artificial Intelligence in Anorexia Nervosa Care: Comparing ChatGPT and Google Gemini. Nutrients, 18(11), 1705. https://doi.org/10.3390/nu18111705

